© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68367
    Prev
    Next
    INDEX
    Explanations

    living people categories

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron does not activate on any of the tokens shown and thus does not appear to detect any specific pattern in these examples.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -1.08
     not
    -1.08
     other
    -1.05
     some
    -1.02
     makeshift
    -1.00
     by
    -0.98
     before
    -0.97
     most
    -0.96
    を
    -0.93
     larger
    -0.91
    POSITIVE LOGITS
     carrinho
    1.23
    獼
    1.13
     lixo
    1.10
     contenedor
    1.09
     estremamente
    1.07
     brilho
    1.06
     avião
    1.06
     Produto
    1.05
     jednod
    1.05
     borbo
    1.05
    Activations Density 0.001%

    No Known Activations